3 files changed, 34 insertions, 8 deletions

diff --git a/README.md b/README.md
index ab11a1c..44b937e 100644
--- a/README.md
+++ b/README.md
@@ -51,7 +51,9 @@ If the parsing process was unsuccessful the HTMLParser will return `false`
 - **weightClasses**: default value `true`, weight classes during the rating phase. 
 - **removeReadabilityTags**: default value `true`, remove the data-readability tags inside the nodes that are added during the rating phase. 
 - **fixRelativeURLs**: default value `false`, convert relative URLs to absolute. Like `/test` to `http://host/test`. 
-- **originalURL**: default value `http://fakehost`, original URL from the article used to fix relative URLs. 
+- **normalizeSpaces**: default value `false`, normalize all spaces. Changes all consecutive spaces to one space. 
+- **substituteEntities**: default value `false`, disables the `substituteEntities` flag of libxml. Will avoid substituting HTML entities. Like `´` to á.
+- **originalURL**: default value `http://fakehost`, original URL from the article used to fix relative URLs.
 
 ## Limitations
 
diff --git a/src/HTMLParser.php b/src/HTMLParser.php
index 5fb27b8..1b1a516 100644
--- a/src/HTMLParser.php
+++ b/src/HTMLParser.php
@@ -35,7 +35,7 @@ class HTMLParser
         'extraneous' => '/print|archive|comment|discuss|e[\-]?mail|share|reply|all|login|sign|single|utility/i',
         'byline' => '/byline|author|dateline|writtenby|p-author/i',
         'replaceFonts' => '/<(\/?)font[^>]*>/gi',
-        'normalize' => '/\s{2,}/g',
+        'normalize' => '/\s{2,}/',
         'videos' => '/\/\/(www\.)?(dailymotion|youtube|youtube-nocookie|player\.vimeo)\.com/i',
         'nextLink' => '/(next|weiter|continue|>([^\|]|$)|»([^\|]|$))/i',
         'prevLink' => '/(prev|earl|old|new|<|«)/i',
@@ -99,6 +99,8 @@ class HTMLParser
             'weightClasses' => true,
             'removeReadabilityTags' => true,
             'fixRelativeURLs' => false,
+            'normalizeSpaces' => false,
+            'substituteEntities' => true,
             'originalURL' => 'http://fakehost',
         ];
 
@@ -202,6 +204,11 @@ class HTMLParser
      */
     private function loadHTML($html)
     {
+        if (!$this->getConfig()->getOption('substituteEntities')) {
+            // Keep the original HTML entities
+            $this->dom->substituteEntities = false;
+        }
+
         // Prepend the XML tag to avoid having issues with special characters. Should be harmless.
         $this->dom->loadHTML('<?xml encoding="UTF-8">' . $html);
         $this->dom->encoding = 'UTF-8';
@@ -334,6 +341,12 @@ class HTMLParser
             }
         }
 
+        if ($this->getConfig()->getOption('normalizeSpaces')) {
+            foreach ($article->getElementsByTagName('p') as $node) {
+                $node->nodeValue = preg_replace($this->regexps['normalize'], ' ', $node->nodeValue);
+            }
+        }
+
         return $article;
     }
 
diff --git a/test/HTMLParserTest.php b/test/HTMLParserTest.php
index c97745d..55b82b8 100644
--- a/test/HTMLParserTest.php
+++ b/test/HTMLParserTest.php
@@ -9,12 +9,19 @@ class HTMLParserTest extends \PHPUnit_Framework_TestCase
     /**
      * @dataProvider getSamplePages
      */
-    public function testHTMLParserParsesHTML($html, $expectedResult, $expectedMetadata)
+    public function testHTMLParserParsesHTML($html, $expectedResult, $expectedMetadata, $config)
     {
-        $readability = new HTMLParser([
-            'originalURL' => 'http://fakehost/test/test.html',
-            'fixRelativeURLs' => true
-        ]);
+        $options = ['originalURL' => 'http://fakehost/test/test.html',
+            'fixRelativeURLs' => true,
+            'normalizeSpaces' => false,
+            'substituteEntities' => true
+        ];
+
+        if ($config) {
+            $options = $config;
+        }
+
+        $readability = new HTMLParser($options);
         $result = $readability->parse($html);
 
         $this->assertEquals($expectedResult, $result['html']);
@@ -34,8 +41,12 @@ class HTMLParserTest extends \PHPUnit_Framework_TestCase
             $source = file_get_contents($path . DIRECTORY_SEPARATOR . $testPage . DIRECTORY_SEPARATOR . 'source.html');
             $expectedHTML = file_get_contents($path . DIRECTORY_SEPARATOR . $testPage . DIRECTORY_SEPARATOR . 'expected.html');
             $expectedMetadata = file_get_contents($path . DIRECTORY_SEPARATOR . $testPage . DIRECTORY_SEPARATOR . 'expected-metadata.json');
+            $config = file_get_contents($path . DIRECTORY_SEPARATOR . $testPage . DIRECTORY_SEPARATOR . 'config.json');
+            if ($config) {
+                $config = json_decode($config);
+            }
 
-            $pages[$testPage] = [$source, $expectedHTML, $expectedMetadata];
+            $pages[$testPage] = [$source, $expectedHTML, $expectedMetadata, $config];
         }
 
         return $pages;